ocr-scanned-pdf

name	ocr-scanned-pdf
description	Use when you have a scanned PDF with no embedded text layer and need to add OCR text

OCR Scanned PDF

Add text recognition to image-only PDFs using ocrmypdf. This preprocesses scanned documents to make them readable by text-extraction tools.

When to use

• Scanned PDF has no text layer (image-only)
• Before running pdf-to-markdown on a scanned document
• User explicitly requests OCR on a specific file

Inputs to gather

• PDF file path (required)
• Language code: --lang (optional; defaults to eng)
• Output path: --out (optional; defaults to <stem>-ocr.pdf next to source)

Procedure

1. Validate that the input PDF exists and is readable.
2. Check if the PDF already has a text layer using pdftotext -layout <pdf> -. If output is substantial, warn the user that OCR may be unnecessary.
3. Run ocrmypdf with sensible defaults: ocrmypdf --language=<lang> <input-pdf> <output-pdf>, where language defaults to eng if not specified.
4. Mention available flags to the user if they need them: --force-ocr (OCR even if text layer exists), --redo-ocr (re-OCR if a layer already exists).
5. Save output to the specified path or <stem>-ocr.pdf next to the source.

Output / side effects

• New PDF file with embedded text layer at the specified output path
• Console confirmation of OCR completion and output location
• Original PDF unchanged

Safety / constraints

• OCR is CPU-intensive; warn user that large PDFs may take several minutes
• Do not overwrite the source PDF; always create a new file